Research map / 3D vision / 3D generation
Volumetric 3D Tracking by Detection
Chun-Hao Huang, Benjamin Allain, Jean-Sebastien Franco, Nassir Navab, Slobodan Ilic, Edmond Boyer
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Regress to volumes (fullCVT) instead of surfaces with CVT features (ablation) | CVT regression forest · Ballet, Thomas matching | percentage of correct matches | Improved |
| Replace voxel features of [16] with CVT features (ablation) | forest of [16] · Ballet, Thomas matching | percentage of correct matches | No clear effect |
| Re-orient data using skeletal poses for [16] (ablation) | forest of [16] · Ballet testing | percentage of correct matches | Improved |
| Multi-template training with Ballet and Thomas added to Goalkeeper (ablation) | fullCVT forest · Goalkeeper UpJump unseen | percentage of correct matches | Improved |
| Volumetric forest-based tracking by detection instead of ICP-only | Thomas 5fps tracking · Thomas low frame rate | median silhouette overlap pixel error: 19998 -> 10054 | Improved |
| Compare against ICP-based volumetric tracking and surface tracking by detection | proposed tracker · Ballet, Goalkeeper, Thomas | silhouette overlap and marker error | Mixed |
Closest papers by meaning
- Prior-free 3D Object Tracking (CVPR 2025 · similarity 0.86)
- Robust 3D Tracking with Quality-Aware Shape Completion (AAAI 2024 · similarity 0.86)
- TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking (NeurIPS 2026 · similarity 0.85)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.84)
- TAPIP3D: Tracking Any Point in Persistent 3D Geometry (NeurIPS 2025 · similarity 0.84)
- DELTA: DENSE EFFICIENT LONG-RANGE 3D TRACKING FOR ANY VIDEO (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
